Frozen vision transformers, applied to image representations of time series, produce classification features that outperform or match time series foundation models on UCR and UEA benchmarks.
Maddix, Hao Wang, Michael W
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Time Series Representations for Classification Lie Hidden in Pretrained Vision Transformers
Frozen vision transformers, applied to image representations of time series, produce classification features that outperform or match time series foundation models on UCR and UEA benchmarks.